Deep Reinforcement Learning for D2D transmission in unlicensed bands.
Zhiqun ZouRui YinXianfu ChenCelimuge WuPublished in: ICCC Workshops (2019)
Keyphrases
- reinforcement learning
- model free
- image registration
- data transmission
- function approximation
- state space
- reinforcement learning algorithms
- pose estimation
- multi agent
- frequency domain
- learning algorithm
- multi agent reinforcement learning
- temporal difference
- optimal control
- markov decision processes
- dynamic programming
- machine learning
- optimal policy
- sensor networks
- hyperspectral images
- action selection
- learning process
- multi agent systems
- transition model
- policy search
- noisy channel
- robotic control